Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge. / Lalande, Alain; Chen, Zhihao; Pommier, Thibaut; Decourselle, Thomas; Qayyum, Abdul; Salomon, Michel; Ginhac, Dominique; Skandarani, Youssef; Boucher, Arnaud; Brahim, Khawla; de Bruijne, Marleen; Camarasa, Robin; Correia, Teresa M; Feng, Xue; Girum, Kibrom B; Hennemuth, Anja; Huellebrand, Markus; Hussain, Raabid; Ivantsits, Matthias; Ma, Jun; Meyer, Craig; Sharma, Rishabh; Shi, Jixi; Tsekos, Nikolaos V; Varela, Marta; Wang, Xiyue; Yang, Sen; Zhang, Hannu; Zhang, Yichi; Zhou, Yuncheng; Zhuang, Xiahai; Couturier, Raphael; Meriaudeau, Fabrice.
In: Medical Image Analysis, Vol. 79, 102428, 2022, p. 1-12.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge
AU - Lalande, Alain
AU - Chen, Zhihao
AU - Pommier, Thibaut
AU - Decourselle, Thomas
AU - Qayyum, Abdul
AU - Salomon, Michel
AU - Ginhac, Dominique
AU - Skandarani, Youssef
AU - Boucher, Arnaud
AU - Brahim, Khawla
AU - de Bruijne, Marleen
AU - Camarasa, Robin
AU - Correia, Teresa M
AU - Feng, Xue
AU - Girum, Kibrom B
AU - Hennemuth, Anja
AU - Huellebrand, Markus
AU - Hussain, Raabid
AU - Ivantsits, Matthias
AU - Ma, Jun
AU - Meyer, Craig
AU - Sharma, Rishabh
AU - Shi, Jixi
AU - Tsekos, Nikolaos V
AU - Varela, Marta
AU - Wang, Xiyue
AU - Yang, Sen
AU - Zhang, Hannu
AU - Zhang, Yichi
AU - Zhou, Yuncheng
AU - Zhuang, Xiahai
AU - Couturier, Raphael
AU - Meriaudeau, Fabrice
N1 - Copyright © 2022. Published by Elsevier B.V.
PY - 2022
Y1 - 2022
N2 - A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed 10 min after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between non-infarct and pathological exams, i.e. exams with or without hyperenhanced area. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases without any hyperenhanced area after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.
AB - A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed 10 min after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between non-infarct and pathological exams, i.e. exams with or without hyperenhanced area. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases without any hyperenhanced area after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.
U2 - 10.1016/j.media.2022.102428
DO - 10.1016/j.media.2022.102428
M3 - Journal article
C2 - 35500498
VL - 79
SP - 1
EP - 12
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 102428
ER -
ID: 305402353